Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1720 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.1226. Min Act: -0.1700

Data Index: 1092234 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0205. Min Act: -0.1700

Data Index: 500341 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0070. Min Act: -0.1700

Data Index: 832730 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9938. Min Act: -0.1700

Data Index: 55102 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9597. Min Act: -0.1700

Data Index: 1358823 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9392. Min Act: -0.1700

Data Index: 338942 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9447. Min Act: -0.1700

Data Index: 470785 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9593. Min Act: -0.1700

Data Index: 116452 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9530. Min Act: -0.1700

Data Index: 707182 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9526. Min Act: -0.1700

Data Index: 402702 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9224. Min Act: -0.1700

Data Index: 417376 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9162. Min Act: -0.1700

Data Index: 1211881 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.8979. Min Act: -0.1700

Data Index: 507572 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9134. Min Act: -0.1700

Data Index: 761706 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9083. Min Act: -0.1700

Data Index: 345070 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9222. Min Act: -0.1700

Data Index: 1345174 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9102. Min Act: -0.1700

Data Index: 709146 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.8807. Min Act: -0.1700

Data Index: 710716 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.8926. Min Act: -0.1700

Data Index: 1025245 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.8762. Min Act: -0.1700

Data Index: 1114699 (C4 (Web Text))

Max Activating Token Index: 361